Prognostics uncertainty reduction by fusing on-line monitoring data based on a state-space-based degradation model

• A modeling framework and associated computational techniques for prognostics uncertainty reduction by fusing on-line monitoring data based on a state-space-based degradation model is proposed.
• A mechanism is developed for quantifying and managing uncertainty in a Bayesian framework.
• The particle Markov chain Monte Carlo method provides an efficient computational tool for the developed framework.

The objective of this study is to develop a state-space-based degradation model and associated computational techniques to reduce failure prognostics uncertainty by fusing on-line monitoring data. A key problem in failure prognostics for an individual system under actual operating conditions is uncertainty management. In this study, the various uncertainty sources in failure prognostics are analyzed, and an appropriate uncertainty quantifying and managing mechanism is proposed, accounting for both the item-to-item variability and the degradation process variability. The method is demonstrated on a crack growth data set, and the results show that the proposed prognostics method has the ability to provide a failure time prediction with less uncertainty by fusing sensor data, which are beneficial for risk assessment and optimal maintenance decision-making.